Fact · Dictation software
39million parameters
The smallest Whisper model, tiny, has 39 million parameters and needs about 1 GB of memory.
Checked against its source on October 16, 2026
In the source's own words
“tiny 39 M tiny.en tiny ~1 GB ~10x”
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision, OpenAI, GitHub (OpenAI repository), 2023, Available models and languages table.
Open the original- What it measures
- The model table in the Whisper README. Its relative speed is measured on an A100 for English speech.
- What it does not show
- The table is OpenAI's measurement. Speed varies with language, speaking speed and hardware.
Source
Cited on
- Dictation Software: How to Choose the Right AppTopic
- Speech Recognition: What It Is and How Well It WorksTopic
- Transcription: How to Turn Audio and Video Into TextTopic
- How to Transcribe Audio to TextGuide
- How to Run Whisper Locally on Your Own ComputerGuide
- Transcribe Audio With Whisper, ChatGPT or GeminiGuide
- Open-Source Dictation Software: Free Apps on GitHubGuide
- Offline Speech to Text on Windows: What WorksGuide